MICCAI 2017 Proceedings, Part III

Abstract

Magnetic Resonance Imaging (MRI) is widely used in routine clinical diagnosis and treatment. However, variations in MRI acquisition protocols result in different appearances of normal and diseased tissue in the images. Convolutional neural networks (CNNs), which have shown to be successful in many medical image analysis tasks, are typically sensitive to the variations in imaging protocols. Therefore, in many cases, networks trained on data acquired with one MRI protocol, do not perform satis-factorily on data acquired with different protocols. This limits the use of models trained with large annotated legacy datasets on a new dataset with a different domain which is often a recurring situation in clinical settings. In this study, we aim to answer the following central questions regarding domain adaptation in medical image analysis: Given a fitted legacy model, (1) How much data from the new domain is required for a decent adapta-tion of the original network?; and, (2) What portion of the pre-trained model parameters should be retrained given a certain number of the new domain training samples? To address these questions, we conducted exten-sive experiments in white matter hyperintensity segmentation task. We trained a CNN on legacy MR images of brain and evaluated the perfor-mance of the domain-adapted network on the same task with images from a different domain. We then compared the performance of the model to the surrogate scenarios where either the same trained network is used or a new network is trained from scratch on the new dataset. The domain-adapted network tuned only by two training examples achieved a Dice score of 0.63 M. Ghafoorian and A. Mehrtash—Contributed equally to this work.